Chain reaction bankruptcy is regarded as common phenomenon and its effect is to be taken into account when credit risk portfolio is analyzed. But consideration and modeling of its effect leave much room for improvemen...Chain reaction bankruptcy is regarded as common phenomenon and its effect is to be taken into account when credit risk portfolio is analyzed. But consideration and modeling of its effect leave much room for improvement. That is mainly because method for grasping relations among companies with limited data is underdeveloped. In this article, chance discovery method is applied to estimate industrial relations that are to include companies＇ relations that transmit chain reaction of bankruptcy. Time order method and directed KeyGraph are newly introduced to distinguish and express the time order among defaults that is essential information for the analysis of chain reaction bankruptcy. The steps for the data analysis are introduced and result of example analysis with default data in Kyushu, Japan, 2005 is presented. The structure estimated by the new method is compared with the structure of actual account receivable holders of bankrupted companies for evaluation.展开更多
It is only the observable part of the real world that can be stored in data. For such incomplete and ill-structured data, data crystallizing aims at presenting the hidden structure among events including unobservable ...It is only the observable part of the real world that can be stored in data. For such incomplete and ill-structured data, data crystallizing aims at presenting the hidden structure among events including unobservable events. This is realized by data crystallization, where dummy items, corresponding to potential existence ofunobservable events, are inserted to the given data. These dummy items and their relations with observable events are visualized by applying KeyGraph to the data with dummy items, like the crystallization of snow where dusts are involved in the formation of crystallization of water molecules. For tuning the granularity level of structure to be visualized, the tool of data crystallization is integrated with human＇s process of understanding significant scenarios in the real world. This basic method is expected to be applicable for various real world domains where previous methods of chance-discovery lead human to successful decision making. In this paper, we apply the data crystallization with human-interactive annealing （DCHA） to the design of products in a real company. The results show its effect to industrial decision making.展开更多
基金The original version was presented on the International Conference on Computational Science (ICCS 2007)
文摘Chain reaction bankruptcy is regarded as common phenomenon and its effect is to be taken into account when credit risk portfolio is analyzed. But consideration and modeling of its effect leave much room for improvement. That is mainly because method for grasping relations among companies with limited data is underdeveloped. In this article, chance discovery method is applied to estimate industrial relations that are to include companies＇ relations that transmit chain reaction of bankruptcy. Time order method and directed KeyGraph are newly introduced to distinguish and express the time order among defaults that is essential information for the analysis of chain reaction bankruptcy. The steps for the data analysis are introduced and result of example analysis with default data in Kyushu, Japan, 2005 is presented. The structure estimated by the new method is compared with the structure of actual account receivable holders of bankrupted companies for evaluation.
文摘It is only the observable part of the real world that can be stored in data. For such incomplete and ill-structured data, data crystallizing aims at presenting the hidden structure among events including unobservable events. This is realized by data crystallization, where dummy items, corresponding to potential existence ofunobservable events, are inserted to the given data. These dummy items and their relations with observable events are visualized by applying KeyGraph to the data with dummy items, like the crystallization of snow where dusts are involved in the formation of crystallization of water molecules. For tuning the granularity level of structure to be visualized, the tool of data crystallization is integrated with human＇s process of understanding significant scenarios in the real world. This basic method is expected to be applicable for various real world domains where previous methods of chance-discovery lead human to successful decision making. In this paper, we apply the data crystallization with human-interactive annealing （DCHA） to the design of products in a real company. The results show its effect to industrial decision making.
